My Learning Journey

Data Analyst in Python 

I completed DataCamp’s Data Analyst with Python career track, consisting of 10 courses, 5 real-world projects, and a timed skills exam focused on data manipulation (score: 84/100). Throughout the program, I learned to clean, analyse, and visualise data using Python, pandas, NumPy, Matplotlib, and Seaborn. I practiced importing data from multiple sources, handling missing values, merging datasets, and performing Exploratory Data Analysis (EDA) to uncover trends and insights. The track also introduced SQL for querying relational databases and integrating structured data into Python workflows. Through hands-on projects, I applied these skills to analsze diverse datasets, including business, environmental, and social data. Overall, the program strengthened my ability to manage the full data analysis workflow; from acquisition and cleaning to visualization and insight communication,
preparing me to deliver data-driven solutions in real-world contexts.

Sampling in Python

I learned to assess the accuracy of sample statistics by calculating relative errors and generating sampling distributions to measure variation in estimates. Working with datasets such as coffee ratings and Spotify tracks, I practiced applying these methods to quantify uncertainty in real-world contexts. A key focus was mastering bootstrapping: using resampling techniques to estimate variation when the underlying population is unknown. This helped me distinguish clearly between sampling and bootstrap distributions, reinforcing how resampling provides a flexible way to support inference and hypothesis testing.

Introduction to Data Visualization with Seaborn

I learned to created and customised plots such as scatter, bar, box, and count plots using real-world datasets. I practised building subplots, adding confidence intervals, and tailoring visualisations to clearly communicate insights. Worked with scatter and line plots to explore relationships between variables also enhanced my quantitative analysis skills. Seaborn is often preferred over Matplotlib for its simpler syntax and attractive defaults, and over Plotly when static, publication-ready visuals are needed.

Web Scraping in Python

I completed a web scraping course in Python, where I learned the structure of HTML, XPath, and CSS selectors to navigate and extract information from web pages. Using the scrapy library, I built simple spiders to crawl sites and automate large-scale data collection, while also gaining transferable skills for libraries like BeautifulSoup and Selenium. This course was both challenging and rewarding, huge thanks to my brother-in-law, Seb Strug, for explaining concepts and helping me with this one!

Introduction to Statistics in Python

I learned core concepts for analysing and interpreting data. I practised working with summary statistics such as mean, median, and standard deviation, and explored probability through random sampling, binomial models, and distributions including normal, Poisson, exponential, and t-distributions. The course also covered correlation, scatterplots, and study design, strengthening my ability to draw reliable conclusions from data using statistical reasoning.

Introduction to Functions in Python

I learned to write custom Python functions tailored to real-world data problems, building up from simple definitions to functions with multiple arguments, return values, default parameters, and variable-length inputs. A key step was understanding scope, ensuring functions behave as intended in different contexts. I also explored lambda functions, which provided a way to write concise, on-the-fly solutions, and practised handling errors to make my code more robust. Along the way, I came to appreciate the importance of writing clear docstrings, recognising how they make functions easier to use, share, and maintain. Applying these skills to Twitter data reinforced how thoughtful function design can streamline analysis and problem solving in data science workflows.

Exploratory Data Analysis in Python

I learned to clean, summarise, and validate both numerical and categorical data. Using real datasets, I practised handling missing values, explored relationships with Seaborn visualisations, and examined case studies such as alcohol use and student performance. A key skill I developed was generating hypotheses from findings, reinforcing how EDA fits into the wider data science workflow and guides the next steps in analysis.

Introduction to Data Visualization with Plotly in Python

I learned to build high-quality, interactive charts directly in Python. I practised creating univariate and bivariate plots, customised visual elements such as annotations, hover effects, and legends, and combined multiple chart types in layered visualisations. The course also covered interactive controls like sliders, buttons, and dropdowns. These skills directly complement my work at Bloomberg, where I use Plotly extensively for data analytics visualisation.

Intermediate Importing Data in Python

I completed an intermediate data importing course in Python, where I learned to access and extract data from the web. This included working with HTML for the first time, scraping and parsing web content, and pulling data from APIs such as OMDB, the Library of Congress, and the Twitter streaming API. Despite using the Bloomberg API daily in Excel and BQuant, this course gave me valuable hands-on experience integrating APIs directly within a Python environment for analysis and visualisation.

Introduction to Importing Data in Python

Here, I learned how to load and manage data from a wide range of sources. I practised importing flat files such as CSV and TXT, as well as working with Excel, SAS, Stata, HDF5, and MATLAB files using NumPy and pandas. The course also introduced relational databases, where I wrote and executed SQL queries to filter, join, and extract meaningful insights from structured data.